batch_rerank · Atlas MCP: Risk & Policy

WHAT IT DOES

What batch_rerank does on Atlas

AI agents invoke batch_rerank to trigger actions in Atlas. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why batch_rerank needs a policy

Reranking involves executing a computational operation (scoring/ordering results) against multiple queries in parallel. It triggers external processing operations rather than simply reading stored data or writing new data. It doesn't delete, move money, or purely retrieve — it actively processes and transforms query results.

From the tool's definition Batch rerank multiple queries in parallel

Risk signalsBulk/mass operation — affects multiple targets

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

batch_rerank Rate-limited

batch_rerank stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "batch_rerank": {
      "limits": [
        {
          "counter": "batch_rerank_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Atlas, so you can run agents against it safely.

FAQ

Questions about batch_rerank

What does the batch_rerank tool do? +

Batch rerank multiple queries in parallel. It is categorised as a Execute tool in the Atlas MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on batch_rerank? +

Register the Atlas MCP server in PolicyLayer and add a rule for batch_rerank: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Atlas. Nothing to install.

What risk level is batch_rerank? +

batch_rerank is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit batch_rerank? +

Yes. Add a rate_limit block to the batch_rerank rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block batch_rerank completely? +

Set action: deny in the PolicyLayer policy for batch_rerank. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides batch_rerank? +

batch_rerank is provided by the Atlas MCP server (rsanandres/atlas_mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.